Triple

T20098615
Position Surface form Disambiguated ID Type / Status
Subject Lady Mary Cavendish E496472 entity
Predicate nobleHouse P13617 FINISHED
Object Devonshire
Devonshire is a prominent English noble house historically associated with the Dukes of Devonshire and the influential Cavendish family.
 E1415451 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Devonshire | Statement: [Lady Mary Cavendish, nobleHouse, Devonshire]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Devonshire
Context triple: [Lady Mary Cavendish, nobleHouse, Devonshire]
  • A. Devon
    Devon is a county in South West England known for its rugged coastlines, moorland national parks, and historic seaside towns.
  • B. Devon
    Devon is a residential neighbourhood located within the city of Fredericton in New Brunswick, Canada.
  • C. Devon
    Devon is a suburban community on the Philadelphia Main Line in Pennsylvania, best known for hosting the historic Devon Horse Show and Country Fair.
  • D. Devon
    Devon is a unisex given name of English origin, often associated with both people and places, including the English county of Devon.
  • E. Devon
    Devon is the central protagonist of the 1970s Canadian science fiction television series "The Starlost," who discovers the truth about his generation starship and seeks to save its inhabitants.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Devonshire
Triple: [Lady Mary Cavendish, nobleHouse, Devonshire]
Generated description
Devonshire is a prominent English noble house historically associated with the Dukes of Devonshire and the influential Cavendish family.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Devonshire
Target entity description: Devonshire is a prominent English noble house historically associated with the Dukes of Devonshire and the influential Cavendish family.
  • A. Devon
    Devon is a county in South West England known for its rugged coastlines, moorland national parks, and historic seaside towns.
  • B. Devon
    Devon is a residential neighbourhood located within the city of Fredericton in New Brunswick, Canada.
  • C. Devon
    Devon is a suburban community on the Philadelphia Main Line in Pennsylvania, best known for hosting the historic Devon Horse Show and Country Fair.
  • D. Devon
    Devon is a unisex given name of English origin, often associated with both people and places, including the English county of Devon.
  • E. Devon
    Devon is the central protagonist of the 1970s Canadian science fiction television series "The Starlost," who discovers the truth about his generation starship and seeks to save its inhabitants.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69da626eee3881909f3454986d4a6511 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6666e306c81909c0ef617e0f6fccf completed April 20, 2026, 5:46 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08346180dc8190b75740c56016ec12 completed May 16, 2026, 9:09 a.m.
NEDg Description generation batch_6a0838867cb081908580ab9594653018 completed May 16, 2026, 9:27 a.m.
NED2 Entity disambiguation (via description) batch_6a083965207c8190babe799e5d45f913 completed May 16, 2026, 9:31 a.m.
Created at: April 11, 2026, 11:25 p.m.